Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2368 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2278. Min Act: -0.0000

Data Index: 101461 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1771279 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2694. Min Act: -0.0000

Data Index: 885747 (The Pile)

Max Activating Token Index: 709

Text #3

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2545. Min Act: -0.0000

Data Index: 963534 (The Pile)

Max Activating Token Index: 1022

Text #4

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2269. Min Act: -0.0000

Data Index: 466362 (The Pile)

Max Activating Token Index: 679

Text #5

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1917431 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2130. Min Act: -0.0000

Data Index: 224805 (The Pile)

Max Activating Token Index: 901

Text #7

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2236. Min Act: -0.0000

Data Index: 875291 (The Pile)

Max Activating Token Index: 653

Text #8

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2272. Min Act: -0.0000

Data Index: 671822 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2049. Min Act: -0.0000

Data Index: 777612 (The Pile)

Max Activating Token Index: 836

Text #10

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1220937 (The Pile)

Max Activating Token Index: 548

Text #11

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1690650 (The Pile)

Max Activating Token Index: 609

Text #12

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1393914 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1906190 (The Pile)

Max Activating Token Index: 917

Text #14

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2005. Min Act: -0.0000

Data Index: 20988 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1826. Min Act: -0.0000

Data Index: 894692 (The Pile)

Max Activating Token Index: 347

Text #16

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1752. Min Act: -0.0000

Data Index: 332237 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1896. Min Act: -0.0000

Data Index: 840252 (The Pile)

Max Activating Token Index: 835

Text #18

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1563068 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1364147 (The Pile)

Max Activating Token Index: 602